arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09722cs.ROcs.AIcs.CV
收藏

Reg-NF:神经场中隐式曲面的高效配准

Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields

CSIRO(联邦科学与工业研究组织);DATA61;Queensland University of Technology (QUT)(昆士兰科技大学)

Stephen Hausler, David Hall, Sutharsan Mahendren, Peyman Moghadam

AI总结:

提出Reg-NF方法,通过双向配准损失、多视图曲面采样和体积符号距离函数,优化两个不同尺度神经场间的6-DoF变换,实现隐式曲面的高效配准。

摘要:

神经场作为基于坐标的神经网络,近期因能够隐式表示场景而广受欢迎。与基于点云等显式表示的经典方法相比,神经场提供了连续的场景表示,能够以紧凑的方式表示3D几何与外观,非常适合机器人应用。然而,以往很少有方法研究通过直接利用这些连续的隐式表示来配准多个神经场。在本文中,我们提出了Reg-NF,一种基于神经场的配准方法,该方法通过优化两个任意神经场之间的相对6自由度(6-DoF)变换,即使这两个场具有不同的尺度因子也能适用。Reg-NF的关键组件包括双向配准损失、多视图曲面采样以及体积符号距离函数(SDFs)的利用。我们在一个新的神经场数据集上展示了该方法,用于评估配准问题。我们提供了一套详尽的实验和消融研究,以验证我们方法的性能,同时讨论了其局限性,从而为研究界在未来解决无约束环境中利用神经场的开放挑战提供方向。

英文摘要:

Neural fields, coordinate-based neural networks, have recently gained popularity for implicitly representing a scene. In contrast to classical methods that are based on explicit representations such as point clouds, neural fields provide a continuous scene representation able to represent 3D geometry and appearance in a way which is compact and ideal for robotics applications. However, limited prior methods have investigated registering multiple neural fields by directly utilising these continuous implicit representations. In this paper, we present Reg-NF, a neural fields-based registration that optimises for the relative 6-DoF transformation between two arbitrary neural fields, even if those two fields have different scale factors. Key components of Reg-NF include a bidirectional registration loss, multi-view surface sampling, and utilisation of volumetric signed distance functions (SDFs). We showcase our approach on a new neural field dataset for evaluating registration problems. We provide an exhaustive set of experiments and ablation studies to identify the performance of our approach, while also discussing limitations to provide future direction to the research community on open challenges in utilizing neural fields in unconstrained environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑